Evaluating Theory of Mind in Reasoning Models: Robustness over Reasoning

2026/08/05 by Ian B. de Haan, Peter van der Putten, Max van Duijn
Computer Science · #cs.CL

paper · pdf

Accepted for 29th International Conference on Discovery Science, October 5-9, 2026, Mainz, Germany

arxiv created 2026/08/05 · arxiv updated 2026/08/06

Abstract

Large language models (LLMs) have recently shown strong performance on Theory of Mind (ToM) tests, prompting debate about the nature and validity of the underlying capabilities. At the same time, reasoning-oriented LLMs trained via reinforcement learning with verifiable rewards have demonstrated notable improvements across a range of benchmarks. In this work, we examine the behavior of such reasoning models in ToM tasks using novel adaptations of machine psychological experiments together with results from established benchmarks. We observe that reasoning models consistently exhibit increased robustness to prompt variations and task perturbations. Our analysis suggests these gains come at least partly from models being more robust at reaching the correct answer under prompt and task variation. We read this as evidence for a robustness-based account rather than for a new ToM-specific ability.

Citations

• DEL-ToM: Inference-Time Scaling for Theory-of-Mind Reasoning via Dynamic Epistemic Logic
• Reasoning Models Don't Always Say What They Think
• Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
• Agentic Large Language Models, a survey
• Towards properly implementing Theory of Mind in AI systems: An account of four misconceptions
• Re-evaluating Theory of Mind evaluation in large language models
• Thinking Slow, Fast: Scaling Inference Compute with Distilled Reasoners
• Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Models
• DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning
• Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
• Multi-Step Reasoning with Large Language Models, a Survey
• LLMs achieve adult human performance on higher-order theory of mind tasks
• ToMBench: Benchmarking Theory of Mind in Large Language Models
• Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind Capabilities
• Theory of Mind in Large Language Models: Examining Performance of 11 State-of-the-Art models vs. Children Aged 7-10 on Advanced Tests
• Large Language Models: The Need for Nuance in Current Debates and a Pragmatic Perspective on Understanding
• FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions
• Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models
• A Survey of Large Language Models
• Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks
• Evaluating large language models in theory of mind tasks
• Does the autistic child have a “theory of mind” ?
• I.—COMPUTING MACHINERY AND INTELLIGENCE